invoke-ai
[bug]: Model Manager can not import LoRa made by FluxGym
Is there an existing issue for this problem?
- [X] I have searched the existing issues
Operating system
Windows
GPU vendor
Nvidia (CUDA)
GPU model
No response
GPU VRAM
No response
Version number
5.0.0
Browser
Brave
Python dependencies
No response
What happened
I crerated a LoRa using FlexGym, carefully leaving all settings on default, except for epochs. When importing this LoRa with model manager, it produces the error.
[2024-09-23 12:28:05,823]::[ModelInstallService]::ERROR --> Model install error: D:/AI/webui_forge/webui/models/Lora/blue-ball.safetensors
InvalidModelConfigException: Unknown LoRA type: D:\AI\webui_forge\webui\models\Lora\blue-ball.safetensors
What you expected to happen
Lora be imported.
How to reproduce the problem
LoRa here: https://zippyshare.day/0kDGvKITOanFlBt/file Download and try to import.
Additional context
This LoRa works successfully in Forge. Has to set mode manually to "bnb-nf4 (fp16 LoRa)". And in Comfy.
Discord username
barafu_albino
These now work. I will reopen if I find particular settings that cause LoRa to not work again.
So, It does not still work in InvokeUI? I've just encountered this error again. How did you solve it?
@arturgromenkov It just worked when I closed the issue. Didn't do anything. Default settings on FluxGym.